University of Birmingham > Talks@bham > Data Science and Computational Statistics Seminar > Computational Optimal Transport Methods and Applications

Computational Optimal Transport Methods and Applications

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Xiaocheng Shang.

While theoretically appealing, the application of optimal transport methods and the related Wasserstein distances to large-scale machine learning problems has been hampered by its prohibitive computational cost. The sliced Wasserstein distance and its variants improve the computational efficiency through random projection, yet they suffer from low projection efficiency because the majority of projections result in trivially small values. In the first part of the talk, I will introduce a new family of sliced Wasserstein distance metrics, called augmented sliced Wasserstein distances (ASWDs), constructed by first mapping samples to higher-dimensional hypersurfaces parameterised by neural networks. In the second part of the talk, I will discuss our applications of optimal transport methods in areas such as reinforcement learning.

Bio: Dr Yunpeng Li is a Senior Lecturer in Artificial Intelligence in the Department of Computer Science at University of Surrey in the UK. His research interests are in the areas of statistical machine learning and signal processing, particularly Bayesian inference techniques, Monte Carlo sampling methods, and the optimal transport theory. He has broad interests in interdisciplinary applications of machine learning including disease detection (breast cancer, dental disease), environmental sensing and object tracking. He received a PhD in Electrical Engineering at the McGill University in Canada in 2017. He was a Postdoctoral Researcher in the Department of Engineering Science at the University of Oxford from 2017 to 2018 and was a Junior Research Fellow at the Wolfson College at the University of Oxford in 2018. He was awarded a Royal Academy of Engineering Enterprise Fellowship in 2023.

This talk is part of the Data Science and Computational Statistics Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on from the University of Cambridge.